CORE-KG: An LLM-Driven Knowledge Graph Construction Framework for Human Smuggling Networks

2025-06-20

AI Summary

To address challenges in legal documents—including non-structural formatting, ambiguous coreference, entity duplication, and relational noise—this paper proposes an automated knowledge graph construction method tailored to human trafficking networks. We introduce a novel type-aware, stepwise large language model (LLM)-based coreference resolution mechanism, integrated with a domain-guided graph-structured extraction paradigm to eliminate reliance on static templates and mitigate hallucination-induced noise. Our approach enhances the GraphRAG framework through structured prompt engineering, domain-specific instruction tuning, and a two-stage LLM pipeline (coreference resolution followed by relation extraction). Experimental results demonstrate a 33.28% reduction in node duplication and a 38.37% decrease in legal text noise, significantly improving graph consistency, interpretability, and analytical utility for downstream forensic and investigative tasks.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Information Extraction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Human smuggling networks are increasingly adaptive and difficult to analyze. Legal case documents offer valuable insights but are unstructured, lexically dense, and filled with ambiguous or shifting references-posing challenges for automated knowledge graph (KG) construction. Existing KG methods often rely on static templates and lack coreference resolution, while recent LLM-based approaches frequently produce noisy, fragmented graphs due to hallucinations, and duplicate nodes caused by a lack of guided extraction. We propose CORE-KG, a modular framework for building interpretable KGs from legal texts. It uses a two-step pipeline: (1) type-aware coreference resolution via sequential, structured LLM prompts, and (2) entity and relationship extraction using domain-guided instructions, built on an adapted GraphRAG framework. CORE-KG reduces node duplication by 33.28%, and legal noise by 38.37% compared to a GraphRAG-based baseline-resulting in cleaner and more coherent graph structures. These improvements make CORE-KG a strong foundation for analyzing complex criminal networks.

Problem

• Analyzing adaptive human smuggling networks from unstructured legal texts
• Overcoming noisy, fragmented knowledge graphs from LLM-based methods
• Reducing node duplication and noise in knowledge graph construction

Innovation

• Type-aware coreference resolution via structured LLM prompts
• Domain-guided entity and relationship extraction
• Adapted GraphRAG framework for cleaner graphs